Recent Trends in Quantitative Structure‐Activity Relationships
Alexander Tropsha · Burger's Medicinal Chemistry and Drug Discovery · 2003
Abstract The field of quantitative structure‐activity relationships (QSARs) as an integral part of computer‐aided drug design and discovery is experiencing one of the most exciting periods in its history. The most important recent developments in the field concur with a substantial increase in the size of experimental data sets available for the analysis and an increased application of QSAR models as virtual screening tools to discover biologically active molecules in chemical databases and/or virtual chemical libraries. Modern QSAR approaches are characterized by the use of multiple descriptors of chemical structure combined with the application of both linear and nonlinear optimization approaches, and a strong emphasis on rigorous model validation, to afford robust and predictive QSAR models. This chapter reviews recent and developing trends in QSAR and offers practical guidelines for the development of reliable QSAR models.